/python/dgl/nn/tensorflow/conv/graphconv.py

"""Tensorflow modules for graph convolutions(GCN)."""
# pylint: disable= no-member, arguments-differ, invalid-name
import tensorflow as tf
from tensorflow.keras import layers
import numpy as np

from .... import function as fn

# pylint: disable=W0235


class GraphConv(layers.Layer):
    r"""Apply graph convolution over an input signal.

    Graph convolution is introduced in `GCN <https://arxiv.org/abs/1609.02907>`__
    and can be described as below:

    .. math::
      h_i^{(l+1)} = \sigma(b^{(l)} + \sum_{j\in\mathcal{N}(i)}\frac{1}{c_{ij}}h_j^{(l)}W^{(l)})

    where :math:`\mathcal{N}(i)` is the neighbor set of node :math:`i`. :math:`c_{ij}` is equal
    to the product of the square root of node degrees:
    :math:`\sqrt{|\mathcal{N}(i)|}\sqrt{|\mathcal{N}(j)|}`. :math:`\sigma` is an activation
    function.

    The model parameters are initialized as in the
    `original implementation <https://github.com/tkipf/gcn/blob/master/gcn/layers.py>`__ where
    the weight :math:`W^{(l)}` is initialized using Glorot uniform initialization
    and the bias is initialized to be zero.

    Notes
    -----
    Zero in degree nodes could lead to invalid normalizer. A common practice
    to avoid this is to add a self-loop for each node in the graph, which
    can be achieved by:

    >>> g = ... # some DGLGraph
    >>> g.add_edges(g.nodes(), g.nodes())


    Parameters
    ----------
    in_feats : int
        Input feature size.
    out_feats : int
        Output feature size.
    norm : str, optional
        How to apply the normalizer. If is `'right'`, divide the aggregated messages
        by each node's in-degrees, which is equivalent to averaging the received messages.
        If is `'none'`, no normalization is applied. Default is `'both'`,
        where the :math:`c_{ij}` in the paper is applied.
    weight : bool, optional
        If True, apply a linear layer. Otherwise, aggregating the messages
        without a weight matrix.
    bias : bool, optional
        If True, adds a learnable bias to the output. Default: ``True``.
    activation: callable activation function/layer or None, optional
        If not None, applies an activation function to the updated node features.
        Default: ``None``.

    Attributes
    ----------
    weight : tf.Tensor
        The learnable weight tensor.
    bias : tf.Tensor
        The learnable bias tensor.
    """

    def __init__(self,
                 in_feats,
                 out_feats,
                 norm='both',
                 weight=True,
                 bias=True,
                 activation=None):
        super(GraphConv, self).__init__()
        if norm not in ('none', 'both', 'right'):
            raise DGLError('Invalid norm value. Must be either "none", "both" or "right".'
                           ' But got "{}".'.format(norm))
        self._in_feats = in_feats
        self._out_feats = out_feats
        self._norm = norm

        if weight:
            xinit = tf.keras.initializers.glorot_uniform()
            self.weight = tf.Variable(initial_value=xinit(
                shape=(in_feats, out_feats), dtype='float32'), trainable=True)
        else:
            self.weight = None

        if bias:
            zeroinit = tf.keras.initializers.zeros()
            self.bias = tf.Variable(initial_value=zeroinit(
                shape=(out_feats), dtype='float32'), trainable=True)
        else:
            self.bias = None

        self._activation = activation

    def call(self, graph, feat, weight=None):
        r"""Compute graph convolution.

        Notes
        -----
        * Input shape: :math:`(N, *, \text{in_feats})` where * means any number of additional
          dimensions, :math:`N` is the number of nodes.
        * Output shape: :math:`(N, *, \text{out_feats})` where all but the last dimension are
          the same shape as the input.
        * Weight shape: "math:`(\text{in_feats}, \text{out_feats})`.

        Parameters
        ----------
        graph : DGLGraph
            The graph.
        feat : tf.Tensor
            The input feature
        weight : torch.Tensor, optional
            Optional external weight tensor.

        Returns
        -------
        tf.Tensor
            The output feature
        """
        graph = graph.local_var()

        if self._norm == 'both':
            degs = tf.clip_by_value(tf.cast(graph.out_degrees(), tf.float32),
                                    clip_value_min=1,
                                    clip_value_max=np.inf)
            norm = tf.pow(degs, -0.5)
            shp = norm.shape + (1,) * (feat.ndim - 1)
            norm = tf.reshape(norm, shp)
            feat = feat * norm

        if weight is not None:
            if self.weight is not None:
                raise DGLError('External weight is provided while at the same time the'
                               ' module has defined its own weight parameter. Please'
                               ' create the module with flag weight=False.')
        else:
            weight = self.weight

        if self._in_feats > self._out_feats:
            # mult W first to reduce the feature size for aggregation.
            if weight is not None:
                feat = tf.matmul(feat, weight)
            graph.srcdata['h'] = feat
            graph.update_all(fn.copy_src(src='h', out='m'),
                             fn.sum(msg='m', out='h'))
            rst = graph.dstdata['h']
        else:
            # aggregate first then mult W
            graph.srcdata['h'] = feat
            graph.update_all(fn.copy_src(src='h', out='m'),
                             fn.sum(msg='m', out='h'))
            rst = graph.dstdata['h']
            if weight is not None:
                rst = tf.matmul(rst, weight)

        if self._norm != 'none':
            degs = tf.clip_by_value(tf.cast(graph.in_degrees(), tf.float32),
                                    clip_value_min=1,
                                    clip_value_max=np.inf)
            if self._norm == 'both':
                norm = tf.pow(degs, -0.5)
            else:
                norm = 1.0 / degs
            shp = norm.shape + (1,) * (feat.ndim - 1)
            norm = tf.reshape(norm, shp)
            rst = rst * norm

        if self.bias is not None:
            rst = rst + self.bias

        if self._activation is not None:
            rst = self._activation(rst)

        return rst

    def extra_repr(self):
        """Set the extra representation of the module,
        which will come into effect when printing the model.
        """
        summary = 'in={_in_feats}, out={_out_feats}'
        summary += ', normalization={_norm}'
        if '_activation' in self.__dict__:
            summary += ', activation={_activation}'
        return summary.format(**self.__dict__)